Functions
magma_int_t	magma_dcustomspmv (magma_int_t m, magma_int_t n, double alpha, double beta, double x, double y, magma_queue_t queue)
	This is an interface to any custom sparse matrix vector product. More...

magma_int_t	magma_dge3pt (magma_int_t m, magma_int_t n, double alpha, double beta, magmaDouble_ptr dx, magmaDouble_ptr dy, magma_queue_t queue)
	This routine is a 3-pt-stencil operator derived from a FD-scheme in 2D with Dirichlet boundary. More...

magma_int_t	magma_dgeaxpy (double alpha, magma_d_matrix X, double beta, magma_d_matrix *Y, magma_queue_t queue)
	This routine computes Y = alpha * X + beta * Y on the GPU. More...

magma_int_t	magma_dgecsr5mv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t p, double alpha, magma_int_t sigma, magma_int_t bit_y_offset, magma_int_t bit_scansum_offset, magma_int_t num_packet, magmaUIndex_ptr dtile_ptr, magmaUIndex_ptr dtile_desc, magmaIndex_ptr dtile_desc_offset_ptr, magmaIndex_ptr dtile_desc_offset, magmaDouble_ptr dcalibrator, magma_int_t tail_tile_start, magmaDouble_ptr dval, magmaIndex_ptr drowptr, magmaIndex_ptr dcolind, magmaDouble_ptr dx, double beta, magmaDouble_ptr dy, magma_queue_t queue)
	This routine computes y = alpha * A * x + beta * y on the GPU. More...

magma_int_t	magma_dgecsrmv (magma_trans_t transA, magma_int_t m, magma_int_t n, double alpha, magmaDouble_ptr dval, magmaIndex_ptr drowptr, magmaIndex_ptr dcolind, magmaDouble_ptr dx, double beta, magmaDouble_ptr dy, magma_queue_t queue)
	This routine computes y = alpha * A * x + beta * y on the GPU. More...

magma_int_t	magma_dgecsrmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, double alpha, double lambda, magmaDouble_ptr dval, magmaIndex_ptr drowptr, magmaIndex_ptr dcolind, magmaDouble_ptr dx, double beta, magma_int_t offset, magma_int_t blocksize, magma_index_t *addrows, magmaDouble_ptr dy, magma_queue_t queue)
	This routine computes y = alpha * ( A -lambda I ) * x + beta * y on the GPU. More...

magma_int_t	magma_dgecsrreimsplit (magma_d_matrix A, magma_d_matrix ReA, magma_d_matrix ImA, magma_queue_t queue)
	This routine takes an input matrix A in CSR format and located on the GPU and splits it into two matrixes ReA and ImA containing the real and the imaginary contributions of A. More...

magma_int_t	magma_dgedensereimsplit (magma_d_matrix A, magma_d_matrix ReA, magma_d_matrix ImA, magma_queue_t queue)
	This routine takes an input matrix A in DENSE format and located on the GPU and splits it into two matrixes ReA and ImA containing the real and the imaginary contributions of A. More...

magma_int_t	magma_dgeellmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, double alpha, magmaDouble_ptr dval, magmaIndex_ptr dcolind, magmaDouble_ptr dx, double beta, magmaDouble_ptr dy, magma_queue_t queue)
	This routine computes y = alpha * A * x + beta * y on the GPU. More...

magma_int_t	magma_dgeellmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, double alpha, double lambda, magmaDouble_ptr dval, magmaIndex_ptr dcolind, magmaDouble_ptr dx, double beta, magma_int_t offset, magma_int_t blocksize, magmaIndex_ptr addrows, magmaDouble_ptr dy, magma_queue_t queue)
	This routine computes y = alpha ( A - lambda I ) x + beta * y on the GPU. More...

magma_int_t	magma_dgeellrtmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, double alpha, magmaDouble_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowlength, magmaDouble_ptr dx, double beta, magmaDouble_ptr dy, magma_int_t alignment, magma_int_t blocksize, magma_queue_t queue)
	This routine computes y = alpha * A * x + beta * y on the GPU. More...

magma_int_t	magma_dgeelltmv_shift (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t nnz_per_row, double alpha, double lambda, magmaDouble_ptr dval, magmaIndex_ptr dcolind, magmaDouble_ptr dx, double beta, magma_int_t offset, magma_int_t blocksize, magmaIndex_ptr addrows, magmaDouble_ptr dy, magma_queue_t queue)
	This routine computes y = alpha ( A - lambda I ) x + beta * y on the GPU. More...

magma_int_t	magma_dmdotc (magma_int_t n, magma_int_t k, magmaDouble_ptr v, magmaDouble_ptr r, magmaDouble_ptr d1, magmaDouble_ptr d2, magmaDouble_ptr skp, magma_queue_t queue)
	Computes the scalar product of a set of vectors v_i such that. More...

magma_int_t	magma_dgesellpmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t blocksize, magma_int_t slices, magma_int_t alignment, double alpha, magmaDouble_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowptr, magmaDouble_ptr dx, double beta, magmaDouble_ptr dy, magma_queue_t queue)
	This routine computes y = alpha * A^t * x + beta * y on the GPU. More...

magma_int_t	magma_dgesellcmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t blocksize, magma_int_t slices, magma_int_t alignment, double alpha, magmaDouble_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowptr, magmaDouble_ptr dx, double beta, magmaDouble_ptr dy, magma_queue_t queue)
	This routine computes y = alpha * A^t * x + beta * y on the GPU. More...

magma_int_t	magma_dmdotc_shfl (magma_int_t n, magma_int_t k, magmaDouble_ptr v, magmaDouble_ptr r, magmaDouble_ptr d1, magmaDouble_ptr d2, magmaDouble_ptr skp, magma_queue_t queue)
	Computes the scalar product of a set of vectors v_i such that. More...

magma_int_t	magma_dmdotc4 (magma_int_t n, magmaDouble_ptr v0, magmaDouble_ptr w0, magmaDouble_ptr v1, magmaDouble_ptr w1, magmaDouble_ptr v2, magmaDouble_ptr w2, magmaDouble_ptr v3, magmaDouble_ptr w3, magmaDouble_ptr d1, magmaDouble_ptr d2, magmaDouble_ptr skp, magma_queue_t queue)
	Computes the scalar product of a set of 4 vectors such that. More...

magma_int_t	magma_dmgecsrmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, double alpha, magmaDouble_ptr dval, magmaIndex_ptr drowptr, magmaIndex_ptr dcolind, magmaDouble_ptr dx, double beta, magmaDouble_ptr dy, magma_queue_t queue)
	This routine computes Y = alpha * A * X + beta * Y for X and Y sets of num_vec vectors on the GPU. More...

magma_int_t	magma_dmgeellmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, magma_int_t nnz_per_row, double alpha, magmaDouble_ptr dval, magmaIndex_ptr dcolind, magmaDouble_ptr dx, double beta, magmaDouble_ptr dy, magma_queue_t queue)
	This routine computes Y = alpha * A * X + beta * Y for X and Y sets of num_vec vectors on the GPU. More...

magma_int_t	magma_dmgeelltmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, magma_int_t nnz_per_row, double alpha, magmaDouble_ptr dval, magmaIndex_ptr dcolind, magmaDouble_ptr dx, double beta, magmaDouble_ptr dy, magma_queue_t queue)
	This routine computes Y = alpha * A * X + beta * Y for X and Y sets of num_vec vectors on the GPU. More...

magma_int_t	magma_dmgesellpmv (magma_trans_t transA, magma_int_t m, magma_int_t n, magma_int_t num_vecs, magma_int_t blocksize, magma_int_t slices, magma_int_t alignment, double alpha, magmaDouble_ptr dval, magmaIndex_ptr dcolind, magmaIndex_ptr drowptr, magmaDouble_ptr dx, double beta, magmaDouble_ptr dy, magma_queue_t queue)
	This routine computes Y = alpha * A^t * X + beta * Y on the GPU. More...

magma_int_t	magma_d_spmv (double alpha, magma_d_matrix A, magma_d_matrix x, double beta, magma_d_matrix y, magma_queue_t queue)
	For a given input matrix A and vectors x, y and scalars alpha, beta the wrapper determines the suitable SpMV computing y = alpha * A * x + beta * y. More...

magma_int_t	magma_d_spmv_shift (double alpha, magma_d_matrix A, double lambda, magma_d_matrix x, double beta, magma_int_t offset, magma_int_t blocksize, magma_index_t *add_rows, magma_d_matrix y, magma_queue_t queue)
	For a given input matrix A and vectors x, y and scalars alpha, beta the wrapper determines the suitable SpMV computing y = alpha * ( A - lambda I ) * x + beta * y. More...

magma_int_t	magma_d_spmm (double alpha, magma_d_matrix A, magma_d_matrix B, magma_d_matrix *C, magma_queue_t queue)
	For a given input matrix A and B and scalar alpha, the wrapper determines the suitable SpMV computing C = alpha * A * B. More...

magma_int_t	magma_dcuspaxpy (double alpha, magma_d_matrix A, double beta, magma_d_matrix B, magma_d_matrix *AB, magma_queue_t queue)
	This is an interface to the cuSPARSE routine csrgeam computing the sum of two sparse matrices stored in csr format: More...

magma_int_t	magma_dcuspmm (magma_d_matrix A, magma_d_matrix B, magma_d_matrix *AB, magma_queue_t queue)
	This is an interface to the cuSPARSE routine csrmm computing the product of two sparse matrices stored in csr format. More...

Detailed Description

Function Documentation

magma_int_t magma_dcustomspmv	(	magma_int_t	m,
		magma_int_t	n,
		double	alpha,
		double	beta,
		double *	x,
		double *	y,
		magma_queue_t	queue
	)

This is an interface to any custom sparse matrix vector product.

It should compute y = alpha*FUNCTION(x) + beta*y The vectors are located on the device, the scalars on the CPU.

Parameters

[in]	m	magma_int_t number of rows
[in]	n	magma_int_t number of columns
[in]	alpha	double scalar alpha
[in]	x	double * input vector x
[in]	beta	double scalar beta
[out]	y	double * output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dge3pt	(	magma_int_t	m,
		magma_int_t	n,
		double	alpha,
		double	beta,
		magmaDouble_ptr	dx,
		magmaDouble_ptr	dy,
		magma_queue_t	queue
	)

This routine is a 3-pt-stencil operator derived from a FD-scheme in 2D with Dirichlet boundary.

It computes y_i = -2 x_i + x_{i-1} + x_{i+1}

Parameters

[in]	m	magma_int_t number of rows in x and y
[in]	n	magma_int_t number of columns in x and y
[in]	alpha	double scalar multiplier
[in]	beta	double scalar multiplier
[in]	dx	magmaDouble_ptr input vector x
[out]	dy	magmaDouble_ptr output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dgeaxpy	(	double	alpha,
		magma_d_matrix	X,
		double	beta,
		magma_d_matrix *	Y,
		magma_queue_t	queue
	)

This routine computes Y = alpha * X + beta * Y on the GPU.

The input format is magma_d_matrix. It can handle both, dense matrix (vector block) and CSR matrices. For the latter, it interfaces the cuSPARSE library.

Parameters

[in]	alpha	double scalar multiplier.
[in]	X	magma_d_matrix input/output matrix Y.
[in]	beta	double scalar multiplier.
[in,out]	Y	magma_d_matrix* input matrix X.
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dgecsr5mv	(	magma_trans_t	transA,
		magma_int_t	m,
		magma_int_t	n,
		magma_int_t	p,
		double	alpha,
		magma_int_t	sigma,
		magma_int_t	bit_y_offset,
		magma_int_t	bit_scansum_offset,
		magma_int_t	num_packet,
		magmaUIndex_ptr	dtile_ptr,
		magmaUIndex_ptr	dtile_desc,
		magmaIndex_ptr	dtile_desc_offset_ptr,
		magmaIndex_ptr	dtile_desc_offset,
		magmaDouble_ptr	dcalibrator,
		magma_int_t	tail_tile_start,
		magmaDouble_ptr	dval,
		magmaIndex_ptr	drowptr,
		magmaIndex_ptr	dcolind,
		magmaDouble_ptr	dx,
		double	beta,
		magmaDouble_ptr	dy,
		magma_queue_t	queue
	)

This routine computes y = alpha * A * x + beta * y on the GPU.

The input format is CSR5 (val (tile-wise column-major), row_pointer, col (tile-wise column-major), tile_pointer, tile_desc).

Parameters

[in]	transA	magma_trans_t transposition parameter for A
[in]	m	magma_int_t number of rows in A
[in]	n	magma_int_t number of columns in A
[in]	p	magma_int_t number of tiles in A
[in]	alpha	double scalar multiplier
[in]	sigma	magma_int_t sigma in A in CSR5
[in]	bit_y_offset	magma_int_t bit_y_offset in A in CSR5
[in]	bit_scansum_offset	magma_int_t bit_scansum_offset in A in CSR5
[in]	num_packet	magma_int_t num_packet in A in CSR5
[in]	dtile_ptr	magmaUIndex_ptr tilepointer of A in CSR5
[in]	dtile_desc	magmaUIndex_ptr tiledescriptor of A in CSR5
[in]	dtile_desc_offset_ptr	magmaIndex_ptr tiledescriptor_offsetpointer of A in CSR5
[in]	dtile_desc_offset	magmaIndex_ptr tiledescriptor_offsetpointer of A in CSR5
[in]	dcalibrator	magmaDouble_ptr calibrator of A in CSR5
[in]	tail_tile_start	magma_int_t start of the last tile in A
[in]	dval	magmaDouble_ptr array containing values of A in CSR
[in]	dval	magmaDouble_ptr array containing values of A in CSR
[in]	drowptr	magmaIndex_ptr rowpointer of A in CSR
[in]	dcolind	magmaIndex_ptr columnindices of A in CSR
[in]	dx	magmaDouble_ptr input vector x
[in]	beta	double scalar multiplier
[out]	dy	magmaDouble_ptr input/output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dgecsrmv	(	magma_trans_t	transA,
		magma_int_t	m,
		magma_int_t	n,
		double	alpha,
		magmaDouble_ptr	dval,
		magmaIndex_ptr	drowptr,
		magmaIndex_ptr	dcolind,
		magmaDouble_ptr	dx,
		double	beta,
		magmaDouble_ptr	dy,
		magma_queue_t	queue
	)

This routine computes y = alpha * A * x + beta * y on the GPU.

The input format is CSR (val, row, col).

Parameters

[in]	transA	magma_trans_t transposition parameter for A
[in]	m	magma_int_t number of rows in A
[in]	n	magma_int_t number of columns in A
[in]	alpha	double scalar multiplier
[in]	dval	magmaDouble_ptr array containing values of A in CSR
[in]	drowptr	magmaIndex_ptr rowpointer of A in CSR
[in]	dcolind	magmaIndex_ptr columnindices of A in CSR
[in]	dx	magmaDouble_ptr input vector x
[in]	beta	double scalar multiplier
[out]	dy	magmaDouble_ptr input/output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dgecsrmv_shift	(	magma_trans_t	transA,
		magma_int_t	m,
		magma_int_t	n,
		double	alpha,
		double	lambda,
		magmaDouble_ptr	dval,
		magmaIndex_ptr	drowptr,
		magmaIndex_ptr	dcolind,
		magmaDouble_ptr	dx,
		double	beta,
		magma_int_t	offset,
		magma_int_t	blocksize,
		magma_index_t *	addrows,
		magmaDouble_ptr	dy,
		magma_queue_t	queue
	)

This routine computes y = alpha * ( A -lambda I ) * x + beta * y on the GPU.

It is a shifted version of the CSR-SpMV.

Parameters

[in]	transA	magma_trans_t transposition parameter for A
[in]	m	magma_int_t number of rows in A
[in]	n	magma_int_t number of columns in A
[in]	alpha	double scalar multiplier
[in]	lambda	double scalar multiplier
[in]	dval	magmaDouble_ptr array containing values of A in CSR
[in]	drowptr	magmaIndex_ptr rowpointer of A in CSR
[in]	dcolind	magmaIndex_ptr columnindices of A in CSR
[in]	dx	magmaDouble_ptr input vector x
[in]	beta	double scalar multiplier
[in]	offset	magma_int_t in case not the main diagonal is scaled
[in]	blocksize	magma_int_t in case of processing multiple vectors
[in]	addrows	magmaIndex_ptr in case the matrixpowerskernel is used
[out]	dy	magmaDouble_ptr output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dgecsrreimsplit	(	magma_d_matrix	A,
		magma_d_matrix *	ReA,
		magma_d_matrix *	ImA,
		magma_queue_t	queue
	)

This routine takes an input matrix A in CSR format and located on the GPU and splits it into two matrixes ReA and ImA containing the real and the imaginary contributions of A.

The output matrices are allocated within the routine.

Parameters

[in]	A	magma_d_matrix input matrix A.
[out]	ReA	magma_d_matrix* output matrix contaning real contributions.
[out]	ImA	magma_d_matrix* output matrix contaning real contributions.
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dgedensereimsplit	(	magma_d_matrix	A,
		magma_d_matrix *	ReA,
		magma_d_matrix *	ImA,
		magma_queue_t	queue
	)

This routine takes an input matrix A in DENSE format and located on the GPU and splits it into two matrixes ReA and ImA containing the real and the imaginary contributions of A.

The output matrices are allocated within the routine.

Parameters

[in]	A	magma_d_matrix input matrix A.
[out]	ReA	magma_d_matrix* output matrix contaning real contributions.
[out]	ImA	magma_d_matrix* output matrix contaning real contributions.
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dgeellmv	(	magma_trans_t	transA,
		magma_int_t	m,
		magma_int_t	n,
		magma_int_t	nnz_per_row,
		double	alpha,
		magmaDouble_ptr	dval,
		magmaIndex_ptr	dcolind,
		magmaDouble_ptr	dx,
		double	beta,
		magmaDouble_ptr	dy,
		magma_queue_t	queue
	)

This routine computes y = alpha * A * x + beta * y on the GPU.

Input format is ELLPACK.

Parameters

[in]	transA	magma_trans_t transposition parameter for A
[in]	m	magma_int_t number of rows in A
[in]	n	magma_int_t number of columns in A
[in]	nnz_per_row	magma_int_t number of elements in the longest row
[in]	alpha	double scalar multiplier
[in]	dval	magmaDouble_ptr array containing values of A in ELLPACK
[in]	dcolind	magmaIndex_ptr columnindices of A in ELLPACK
[in]	dx	magmaDouble_ptr input vector x
[in]	beta	double scalar multiplier
[out]	dy	magmaDouble_ptr input/output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dgeellmv_shift	(	magma_trans_t	transA,
		magma_int_t	m,
		magma_int_t	n,
		magma_int_t	nnz_per_row,
		double	alpha,
		double	lambda,
		magmaDouble_ptr	dval,
		magmaIndex_ptr	dcolind,
		magmaDouble_ptr	dx,
		double	beta,
		magma_int_t	offset,
		magma_int_t	blocksize,
		magmaIndex_ptr	addrows,
		magmaDouble_ptr	dy,
		magma_queue_t	queue
	)

This routine computes y = alpha *( A - lambda I ) * x + beta * y on the GPU.

Input format is ELLPACK. It is the shifted version of the ELLPACK SpMV.

Parameters

[in]	transA	magma_trans_t transposition parameter for A
[in]	m	magma_int_t number of rows in A
[in]	n	magma_int_t number of columns in A
[in]	nnz_per_row	magma_int_t number of elements in the longest row
[in]	alpha	double scalar multiplier
[in]	lambda	double scalar multiplier
[in]	dval	magmaDouble_ptr array containing values of A in ELLPACK
[in]	dcolind	magmaIndex_ptr columnindices of A in ELLPACK
[in]	dx	magmaDouble_ptr input vector x
[in]	beta	double scalar multiplier
[in]	offset	magma_int_t in case not the main diagonal is scaled
[in]	blocksize	magma_int_t in case of processing multiple vectors
[in]	addrows	magmaIndex_ptr in case the matrixpowerskernel is used
[out]	dy	magmaDouble_ptr input/output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dgeellrtmv	(	magma_trans_t	transA,
		magma_int_t	m,
		magma_int_t	n,
		magma_int_t	nnz_per_row,
		double	alpha,
		magmaDouble_ptr	dval,
		magmaIndex_ptr	dcolind,
		magmaIndex_ptr	drowlength,
		magmaDouble_ptr	dx,
		double	beta,
		magmaDouble_ptr	dy,
		magma_int_t	alignment,
		magma_int_t	blocksize,
		magma_queue_t	queue
	)

This routine computes y = alpha * A * x + beta * y on the GPU.

Input format is ELLRT. The ideas are taken from "Improving the performance of the sparse matrix vector product with GPUs", (CIT 2010), and modified to provide correct values.

Parameters

[in]	transA	magma_trans_t transposition parameter for A
[in]	m	magma_int_t number of rows
[in]	n	magma_int_t number of columns
[in]	nnz_per_row	magma_int_t max number of nonzeros in a row
[in]	alpha	double scalar alpha
[in]	dval	magmaDouble_ptr val array
[in]	dcolind	magmaIndex_ptr col indices
[in]	drowlength	magmaIndex_ptr number of elements in each row
[in]	dx	magmaDouble_ptr input vector x
[in]	beta	double scalar beta
[out]	dy	magmaDouble_ptr output vector y
[in]	blocksize	magma_int_t threads per block
[in]	alignment	magma_int_t threads assigned to each row
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dgeelltmv_shift	(	magma_trans_t	transA,
		magma_int_t	m,
		magma_int_t	n,
		magma_int_t	nnz_per_row,
		double	alpha,
		double	lambda,
		magmaDouble_ptr	dval,
		magmaIndex_ptr	dcolind,
		magmaDouble_ptr	dx,
		double	beta,
		magma_int_t	offset,
		magma_int_t	blocksize,
		magmaIndex_ptr	addrows,
		magmaDouble_ptr	dy,
		magma_queue_t	queue
	)

This routine computes y = alpha *( A - lambda I ) * x + beta * y on the GPU.

Input format is ELL.

Parameters

[in]	transA	magma_trans_t transposition parameter for A
[in]	m	magma_int_t number of rows in A
[in]	n	magma_int_t number of columns in A
[in]	nnz_per_row	magma_int_t number of elements in the longest row
[in]	alpha	double scalar multiplier
[in]	lambda	double scalar multiplier
[in]	dval	magmaDouble_ptr array containing values of A in ELL
[in]	dcolind	magmaIndex_ptr columnindices of A in ELL
[in]	dx	magmaDouble_ptr input vector x
[in]	beta	double scalar multiplier
[in]	offset	magma_int_t in case not the main diagonal is scaled
[in]	blocksize	magma_int_t in case of processing multiple vectors
[in]	addrows	magmaIndex_ptr in case the matrixpowerskernel is used
[out]	dy	magmaDouble_ptr input/output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dmdotc	(	magma_int_t	n,
		magma_int_t	k,
		magmaDouble_ptr	v,
		magmaDouble_ptr	r,
		magmaDouble_ptr	d1,
		magmaDouble_ptr	d2,
		magmaDouble_ptr	skp,
		magma_queue_t	queue
	)

Computes the scalar product of a set of vectors v_i such that.

skp = ( <v_0,r>, <v_1,r>, .. )

Returns the vector skp.

Parameters

[in]	n	int length of v_i and r
[in]	k	int vectors v_i

Parameters

[in]	v	magmaDouble_ptr v = (v_0 .. v_i.. v_k)
[in]	r	magmaDouble_ptr r
[in]	d1	magmaDouble_ptr workspace
[in]	d2	magmaDouble_ptr workspace
[out]	skp	magmaDouble_ptr vector[k] of scalar products (<v_i,r>...)
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dgesellpmv	(	magma_trans_t	transA,
		magma_int_t	m,
		magma_int_t	n,
		magma_int_t	blocksize,
		magma_int_t	slices,
		magma_int_t	alignment,
		double	alpha,
		magmaDouble_ptr	dval,
		magmaIndex_ptr	dcolind,
		magmaIndex_ptr	drowptr,
		magmaDouble_ptr	dx,
		double	beta,
		magmaDouble_ptr	dy,
		magma_queue_t	queue
	)

This routine computes y = alpha * A^t * x + beta * y on the GPU.

Input format is SELLP.

Parameters

[in]	transA	magma_trans_t transposition parameter for A
[in]	m	magma_int_t number of rows in A
[in]	n	magma_int_t number of columns in A
[in]	blocksize	magma_int_t number of rows in one ELL-slice
[in]	slices	magma_int_t number of slices in matrix
[in]	alignment	magma_int_t number of threads assigned to one row
[in]	alpha	double scalar multiplier
[in]	dval	magmaDouble_ptr array containing values of A in SELLP
[in]	dcolind	magmaIndex_ptr columnindices of A in SELLP
[in]	drowptr	magmaIndex_ptr rowpointer of SELLP
[in]	dx	magmaDouble_ptr input vector x
[in]	beta	double scalar multiplier
[out]	dy	magmaDouble_ptr input/output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dgesellcmv	(	magma_trans_t	transA,
		magma_int_t	m,
		magma_int_t	n,
		magma_int_t	blocksize,
		magma_int_t	slices,
		magma_int_t	alignment,
		double	alpha,
		magmaDouble_ptr	dval,
		magmaIndex_ptr	dcolind,
		magmaIndex_ptr	drowptr,
		magmaDouble_ptr	dx,
		double	beta,
		magmaDouble_ptr	dy,
		magma_queue_t	queue
	)

This routine computes y = alpha * A^t * x + beta * y on the GPU.

Input format is SELLC/SELLP.

Parameters

[in]	transA	magma_trans_t transposition parameter for A
[in]	m	magma_int_t number of rows in A
[in]	n	magma_int_t number of columns in A
[in]	blocksize	magma_int_t number of rows in one ELL-slice
[in]	slices	magma_int_t number of slices in matrix
[in]	alignment	magma_int_t number of threads assigned to one row (=1)
[in]	alpha	double scalar multiplier
[in]	dval	magmaDouble_ptr array containing values of A in SELLC/P
[in]	dcolind	magmaIndex_ptr columnindices of A in SELLC/P
[in]	drowptr	magmaIndex_ptr rowpointer of SELLP
[in]	dx	magmaDouble_ptr input vector x
[in]	beta	double scalar multiplier
[out]	dy	magmaDouble_ptr input/output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dmdotc_shfl	(	magma_int_t	n,
		magma_int_t	k,
		magmaDouble_ptr	v,
		magmaDouble_ptr	r,
		magmaDouble_ptr	d1,
		magmaDouble_ptr	d2,
		magmaDouble_ptr	skp,
		magma_queue_t	queue
	)

Computes the scalar product of a set of vectors v_i such that.

skp = ( <v_0,r>, <v_1,r>, .. )

Returns the vector skp.

Parameters

[in]	n	int length of v_i and r
[in]	k	int vectors v_i

Parameters

[in]	v	magmaDouble_ptr v = (v_0 .. v_i.. v_k)
[in]	r	magmaDouble_ptr r
[in]	d1	magmaDouble_ptr workspace
[in]	d2	magmaDouble_ptr workspace
[out]	skp	magmaDouble_ptr vector[k] of scalar products (<v_i,r>...)
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dmdotc4	(	magma_int_t	n,
		magmaDouble_ptr	v0,
		magmaDouble_ptr	w0,
		magmaDouble_ptr	v1,
		magmaDouble_ptr	w1,
		magmaDouble_ptr	v2,
		magmaDouble_ptr	w2,
		magmaDouble_ptr	v3,
		magmaDouble_ptr	w3,
		magmaDouble_ptr	d1,
		magmaDouble_ptr	d2,
		magmaDouble_ptr	skp,
		magma_queue_t	queue
	)

Computes the scalar product of a set of 4 vectors such that.

skp[0,1,2,3] = [ <v_0,w_0>, <v_1,w_1>, <v_2,w_2>, <v3,w_3> ]

Returns the vector skp. In case there are less dot products required, an easy workaround is given by doubling input.

Parameters

[in]	n	int length of v_i and w_i
[in]	v0	magmaDouble_ptr input vector
[in]	w0	magmaDouble_ptr input vector
[in]	v1	magmaDouble_ptr input vector
[in]	w1	magmaDouble_ptr input vector
[in]	v2	magmaDouble_ptr input vector
[in]	w2	magmaDouble_ptr input vector
[in]	v3	magmaDouble_ptr input vector
[in]	w3	magmaDouble_ptr input vector
[in]	d1	magmaDouble_ptr workspace
[in]	d2	magmaDouble_ptr workspace
[out]	skp	magmaDouble_ptr vector[4] of scalar products [<v_i, w_i>] This vector is located on the host
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dmgecsrmv	(	magma_trans_t	transA,
		magma_int_t	m,
		magma_int_t	n,
		magma_int_t	num_vecs,
		double	alpha,
		magmaDouble_ptr	dval,
		magmaIndex_ptr	drowptr,
		magmaIndex_ptr	dcolind,
		magmaDouble_ptr	dx,
		double	beta,
		magmaDouble_ptr	dy,
		magma_queue_t	queue
	)

This routine computes Y = alpha * A * X + beta * Y for X and Y sets of num_vec vectors on the GPU.

Input format is CSR.

Parameters

[in]	transA	magma_trans_t transposition parameter for A
[in]	m	magma_int_t number of rows in A
[in]	n	magma_int_t number of columns in A
[in]	num_vecs	mama_int_t number of vectors
[in]	alpha	double scalar multiplier
[in]	dval	magmaDouble_ptr array containing values of A in CSR
[in]	drowptr	magmaIndex_ptr rowpointer of A in CSR
[in]	dcolind	magmaIndex_ptr columnindices of A in CSR
[in]	dx	magmaDouble_ptr input vector x
[in]	beta	double scalar multiplier
[out]	dy	magmaDouble_ptr input/output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dmgeellmv	(	magma_trans_t	transA,
		magma_int_t	m,
		magma_int_t	n,
		magma_int_t	num_vecs,
		magma_int_t	nnz_per_row,
		double	alpha,
		magmaDouble_ptr	dval,
		magmaIndex_ptr	dcolind,
		magmaDouble_ptr	dx,
		double	beta,
		magmaDouble_ptr	dy,
		magma_queue_t	queue
	)

This routine computes Y = alpha * A * X + beta * Y for X and Y sets of num_vec vectors on the GPU.

Input format is ELLPACK.

Parameters

[in]	transA	magma_trans_t transposition parameter for A
[in]	m	magma_int_t number of rows in A
[in]	n	magma_int_t number of columns in A
[in]	num_vecs	mama_int_t number of vectors
[in]	nnz_per_row	magma_int_t number of elements in the longest row
[in]	alpha	double scalar multiplier
[in]	dval	magmaDouble_ptr array containing values of A in ELLPACK
[in]	dcolind	magmaIndex_ptr columnindices of A in ELLPACK
[in]	dx	magmaDouble_ptr input vector x
[in]	beta	double scalar multiplier
[out]	dy	magmaDouble_ptr input/output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dmgeelltmv	(	magma_trans_t	transA,
		magma_int_t	m,
		magma_int_t	n,
		magma_int_t	num_vecs,
		magma_int_t	nnz_per_row,
		double	alpha,
		magmaDouble_ptr	dval,
		magmaIndex_ptr	dcolind,
		magmaDouble_ptr	dx,
		double	beta,
		magmaDouble_ptr	dy,
		magma_queue_t	queue
	)

This routine computes Y = alpha * A * X + beta * Y for X and Y sets of num_vec vectors on the GPU.

Input format is ELL.

Parameters

[in]	transA	magma_trans_t transposition parameter for A
[in]	m	magma_int_t number of rows in A
[in]	n	magma_int_t number of columns in A
[in]	num_vecs	mama_int_t number of vectors
[in]	nnz_per_row	magma_int_t number of elements in the longest row
[in]	alpha	double scalar multiplier
[in]	dval	magmaDouble_ptr array containing values of A in ELL
[in]	dcolind	magmaIndex_ptr columnindices of A in ELL
[in]	dx	magmaDouble_ptr input vector x
[in]	beta	double scalar multiplier
[out]	dy	magmaDouble_ptr input/output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dmgesellpmv	(	magma_trans_t	transA,
		magma_int_t	m,
		magma_int_t	n,
		magma_int_t	num_vecs,
		magma_int_t	blocksize,
		magma_int_t	slices,
		magma_int_t	alignment,
		double	alpha,
		magmaDouble_ptr	dval,
		magmaIndex_ptr	dcolind,
		magmaIndex_ptr	drowptr,
		magmaDouble_ptr	dx,
		double	beta,
		magmaDouble_ptr	dy,
		magma_queue_t	queue
	)

This routine computes Y = alpha * A^t * X + beta * Y on the GPU.

Input format is SELLP. Note, that the input format for X is row-major while the output format for Y is column major!

Parameters

[in]	transA	magma_trans_t transpose A?
[in]	m	magma_int_t number of rows in A
[in]	n	magma_int_t number of columns in A
[in]	num_vecs	magma_int_t number of columns in X and Y
[in]	blocksize	magma_int_t number of rows in one ELL-slice
[in]	slices	magma_int_t number of slices in matrix
[in]	alignment	magma_int_t number of threads assigned to one row
[in]	alpha	double scalar multiplier
[in]	dval	magmaDouble_ptr array containing values of A in SELLP
[in]	dcolind	magmaIndex_ptr columnindices of A in SELLP
[in]	drowptr	magmaIndex_ptr rowpointer of SELLP
[in]	dx	magmaDouble_ptr input vector x
[in]	beta	double scalar multiplier
[out]	dy	magmaDouble_ptr input/output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_d_spmv	(	double	alpha,
		magma_d_matrix	A,
		magma_d_matrix	x,
		double	beta,
		magma_d_matrix	y,
		magma_queue_t	queue
	)

For a given input matrix A and vectors x, y and scalars alpha, beta the wrapper determines the suitable SpMV computing y = alpha * A * x + beta * y.

Parameters

[in]	alpha	double scalar alpha
[in]	A	magma_d_matrix sparse matrix A
[in]	x	magma_d_matrix input vector x
[in]	beta	double scalar beta
[out]	y	magma_d_matrix output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_d_spmv_shift	(	double	alpha,
		magma_d_matrix	A,
		double	lambda,
		magma_d_matrix	x,
		double	beta,
		magma_int_t	offset,
		magma_int_t	blocksize,
		magma_index_t *	add_rows,
		magma_d_matrix	y,
		magma_queue_t	queue
	)

For a given input matrix A and vectors x, y and scalars alpha, beta the wrapper determines the suitable SpMV computing y = alpha * ( A - lambda I ) * x + beta * y.

Parameters

	alpha	double scalar alpha
	A	magma_d_matrix sparse matrix A
	lambda	double scalar lambda
	x	magma_d_matrix input vector x
	beta	double scalar beta
	offset	magma_int_t in case not the main diagonal is scaled
	blocksize	magma_int_t in case of processing multiple vectors
	add_rows	magma_int_t* in case the matrixpowerskernel is used
	y	magma_d_matrix output vector y
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_d_spmm	(	double	alpha,
		magma_d_matrix	A,
		magma_d_matrix	B,
		magma_d_matrix *	C,
		magma_queue_t	queue
	)

For a given input matrix A and B and scalar alpha, the wrapper determines the suitable SpMV computing C = alpha * A * B.

Parameters

[in]	alpha	double scalar alpha
[in]	A	magma_d_matrix sparse matrix A
[in]	B	magma_d_matrix sparse matrix C
[out]	C	magma_d_matrix * outpur sparse matrix C
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dcuspaxpy	(	double *	alpha,
		magma_d_matrix	A,
		double *	beta,
		magma_d_matrix	B,
		magma_d_matrix *	AB,
		magma_queue_t	queue
	)

This is an interface to the cuSPARSE routine csrgeam computing the sum of two sparse matrices stored in csr format:

C = alpha * A + beta * B

Parameters

[in]	alpha	double* scalar
[in]	A	magma_d_matrix input matrix
[in]	beta	double* scalar
[in]	B	magma_d_matrix input matrix
[out]	AB	magma_d_matrix* output matrix AB = alpha * A + beta * B
[in]	queue	magma_queue_t Queue to execute in.

magma_int_t magma_dcuspmm	(	magma_d_matrix	A,
		magma_d_matrix	B,
		magma_d_matrix *	AB,
		magma_queue_t	queue
	)

This is an interface to the cuSPARSE routine csrmm computing the product of two sparse matrices stored in csr format.

Parameters

[in]	A	magma_d_matrix input matrix
[in]	B	magma_d_matrix input matrix
[out]	AB	magma_d_matrix* output matrix AB = A * B
[in]	queue	magma_queue_t Queue to execute in.

Functions

Detailed Description

Function Documentation

vectors v_i

vectors v_i